U.S. patent application number 10/957482 was filed with the patent office on 2006-04-06 for systems and methods for hands-free voice-activated devices.
This patent application is currently assigned to Siemens Information and Communication Mobile, LLC, Siemens Information and Communication Mobile, LLC. Invention is credited to Lovleen Chadha.
Application Number | 20060074658 10/957482 |
Document ID | / |
Family ID | 36126668 |
Filed Date | 2006-04-06 |
United States Patent
Application |
20060074658 |
Kind Code |
A1 |
Chadha; Lovleen |
April 6, 2006 |
Systems and methods for hands-free voice-activated devices
Abstract
In some embodiments, systems and methods for hands-free
voice-activated devices include devices that are capable of
recognizing voice commands from specific users. According to some
embodiments, hands-free voice-activated devices may also or
alternatively be responsive to an activation identifier.
Inventors: |
Chadha; Lovleen; (San Diego,
CA) |
Correspondence
Address: |
SIEMENS CORPORATION;INTELLECTUAL PROPERTY DEPARTMENT
170 WOOD AVENUE SOUTH
ISELIN
NJ
08830
US
|
Assignee: |
Siemens Information and
Communication Mobile, LLC
|
Family ID: |
36126668 |
Appl. No.: |
10/957482 |
Filed: |
October 1, 2004 |
Current U.S.
Class: |
704/246 ;
704/E15.045; 704/E17.003 |
Current CPC
Class: |
G10L 15/26 20130101;
G10L 17/00 20130101; H04M 1/271 20130101 |
Class at
Publication: |
704/246 |
International
Class: |
G10L 17/00 20060101
G10L017/00 |
Claims
1. A method, comprising: receiving voice input; determining if the
voice input is associated with a recognized user; determining, in
the case that the voice input is associated with the recognized
user, a command associated with the voice input; and executing the
command.
2. The method of claim 1, further comprising: initiating an
activation state in the case that the voice input is associated
with the recognized user.
3. The method of claim 2, further comprising: listening, during the
activation state, for voice commands provided by the recognized
user.
4. The method of claim 2, further comprising: terminating the
activation state upon the occurrence of an event.
5. The method of claim 4, wherein the event includes at least one
of a lapse of a time period or a receipt of a termination
command.
6. The method of claim 1, further comprising: learning to identify
voice input from the recognized user.
7. The method of claim 6, wherein the learning is conducted for
each of a plurality of recognized users.
8. The method of claim 1, wherein the determining the command
includes: comparing at least one portion of the voice input to a
plurality of stored voice input commands.
9. The method of claim 1, wherein the determining the command
includes: interpreting a natural language of the voice input to
determine the command.
10. A method, comprising: receiving voice input; determining if the
voice input is associated with a recognized activation identifier;
and initiating an activation state in the case that the voice input
is associated with the recognized activation identifier.
11. The method of claim 10, further comprising: determining, in the
case that the voice input is associated with a recognized
activation identifier, a command associated with the voice input;
and executing the command.
12. The method of claim 11, wherein the determining the command
includes: comparing at least one portion of the voice input to a
plurality of stored voice input commands.
13. The method of claim 11, wherein the determining the command
includes: interpreting a natural language of the voice input to
determine the command.
14. The method of claim 10, wherein the activation state is only
initiated in the case that the recognized activation identifier is
identified as being provided by a recognized user.
15. The method of claim 10, further comprising: listening, during
the activation state, for voice commands provided by a recognized
user.
16. The method of claim 15, further comprising: learning to
identify voice input from the recognized user.
17. The method of claim 16, wherein the learning is conducted for
each of a plurality of recognized users.
18. The method of claim 10, further comprising: terminating the
activation state upon the occurrence of an event.
19. The method of claim 18, wherein the event includes at least one
of a lapse of a time period or a receipt of a termination
command.
20. A system, comprising: a memory configured to store
instructions; a communication port; and a processor coupled to the
memory and the communication port, the processor being configured
to execute the stored instructions to: receive voice input;
determine if the voice input is associated with a recognized user;
determine, in the case that the voice input is associated with a
recognized user, a command associated with the voice input; and
execute the command.
Description
TECHNICAL FIELD
[0001] The present disclosure relates generally to systems and
methods for voice-activated devices, and more particularly to
systems and methods for hands-free voice-activated devices.
BACKGROUND
[0002] Electronic devices, such as cellular telephones and
computers, are often used in situations where the user is unable to
easily utilize typical input components to control the devices.
Using a mouse, typing information into a keyboard, or even making a
selection from a touch screen display may, for example, be
difficult, dangerous, or impossible in certain circumstances (e.g.,
while driving a car or when both of a user's hands are already
being used).
[0003] Many electronic devices have been equipped with
voice-activation capabilities, allowing a user to control a device
using voice commands. These devices however, still require a user
to interact with the device by utilizing a typical input component
in order to access the voice-activation feature. Cellular
telephones, for example, require a user to press a button that
causes the cell phone to "listen" for the user's command. Thus,
users of voice-activated devices must physically interact with the
devices to initiate voice-activation features. Such physical
interaction may still be incompatible with or undesirable in
certain situations.
[0004] Accordingly, there is a need for systems and methods for
improved voice-activated devices, and particularly for hands-free
voice-activated devices, that address these and other problems
found in existing technologies.
SUMMARY
[0005] Methods, systems, and computer program code are therefore
presented for providing hands-free voice-activated devices.
[0006] According to some embodiments, systems, methods, and
computer code are operable to receive voice input, determine if the
voice input is associated with a recognized user, determine, in the
case that the voice input is associated with the recognized user, a
command associated with the voice input, and execute the command.
Embodiments may further be operable to initiate an activation state
in the case that the voice input is associated with the recognized
user and/or to learn to identify voice input from the recognized
user.
[0007] According to some embodiments, systems, methods, and
computer code are operable to receive voice input, determine if the
voice input is associated with a recognized activation identifier,
and initiate an activation state in the case that the voice input
is associated with the recognized activation identifier.
Embodiments may further be operable to determine, in the case that
the voice input is associated with a recognized activation
identifier, a command associated with the voice input, and execute
the command.
[0008] With these and other advantages and features of embodiments
that will become hereinafter apparent, embodiments may be more
clearly understood by reference to the following detailed
description, the appended claims and the drawings attached
herein.
BRIEF DESCRIPTION OF THE DRAWINGS
[0009] FIG. 1 is a block diagram of a system according to some
embodiments;
[0010] FIG. 2 is a flowchart of a method according to some
embodiments;
[0011] FIG. 3 is a flowchart of a method according to some
embodiments;
[0012] FIG. 4 is a perspective diagram of an exemplary system
according to some embodiments;
[0013] FIG. 5 is a block diagram of a system according to some
embodiments; and
[0014] FIG. 6 is a block diagram of a system according to some
embodiments.
DETAILED DESCRIPTION
[0015] Some embodiments described herein are associated with a
"user device" or a "voice-activated device". As used herein, the
term "user device" may generally refer to any type and/or
configuration of device that can be programmed, manipulated, and/or
otherwise utilized by a user. Examples of user devices include a
Personal Computer (PC) device, a workstation, a server, a printer,
a scanner, a facsimile machine, a camera, a copier, a Personal
Digital Assistant (PDA) device, a modem, and/or a wireless phone.
In some embodiments, a user device may be a device that is
configured to conduct and/or facilitate communications (e.g., a
cellular telephone, a Voice over Internet Protocol (VoIP) device,
and/or a walkie-talkie). According to some embodiments, a user
device may be or include a "voice-activated device". As used
herein, the term "voice-activated device" may generally refer to
any user device that is operable to receive, process, and/or
otherwise utilize voice input. In some embodiments, a
voice-activated device may be a device that is configured to
execute voice commands received from a user. According to some
embodiments, a voice-activated device may be a user device that is
operable to enter and/or initialize an activation state in response
to a user's voice.
[0016] Referring first to FIG. 1, a block diagram of a system 100
according to some embodiments is shown. The various systems
described herein are depicted for use in explanation, but not
limitation, of described embodiments. Different types, layouts,
quantities, and configurations of any of the systems described
herein may be used without deviating from the scope of some
embodiments. Fewer or more components than are shown in relation to
the systems described herein may be utilized without deviating from
some embodiments.
[0017] The system 100 may comprise, for example, one or more user
devices 110a-d. The user devices 110a-d may be or include any
quantity, type, and/or configuration of devices that are or become
known or practicable. In some embodiments, one or more of the user
devices 110a-d may be associated with one or more users. The user
devices 110a-d may, according to some embodiments, be situated in
one or more environments. The system 100 may, for example, be or
include an environment such as a room, a building, and/or any other
type of area or location.
[0018] Within the environment, the user devices 10a-d may be
exposed to various sounds 120. The sounds 120 may include, for
example, traffic sounds (e.g., vehicle noise), machinery and/or
equipment sounds (e.g., heating and ventilating sounds, copier
sounds, or fluorescent light sounds), natural sounds (e.g., rain,
birds, and/or wind), and/or other sounds. In some embodiments, the
sounds 120 may include voice sounds 130. Voice sounds 130 may, for
example, be or include voices originating from a person, a
television, a radio, and/or may include synthetic voice sounds.
According to some embodiments, the voice sounds 130 may include
voice commands 140. The voice commands 140 may, in some
embodiments, be or include voice sounds 130 intended as input to
one or more of the user devices 110a-d. According to some
embodiments, the voice commands 140 may include commands that are
intended for a particular user device 110a-d.
[0019] One or more of the user devices 110a-d may, for example, be
voice-activated devices that accept voice input such as the voice
commands 140. In some embodiments, the user devices 110a-d may be
operable to identify the voice commands 140. The user devices
110a-d may, for example, be capable of determining which of the
sounds 120 are voice commands 140. In some embodiments, a
particular user device 10a-d such as the first user device 10a may
be operable to determine which of the voice commands 140 (if any)
are intended for the first user device 110a.
[0020] One advantage to some embodiments is that because the user
devices 110a-d are capable of distinguishing the voice commands 140
from the other voice sounds 130, from the sounds 120, and/or from
voice commands 140 not intended for a particular user device
110a-d, the user devices 110a-d may not require any physical
interaction to activate voice-response features. In such a manner,
for example, some embodiments facilitate and/or allow hands-free
operation of the user devices 110a-d. In other words, voice
commands 140 intended for the first user device 110a may be
identified, by the first user device 110a, from among all of the
sounds 120 within the environment.
[0021] In some embodiments, such a capability may permit
voice-activation features of a user device 110a-d to be initiated
and/or utilized without the need for physical interaction with the
user device 110a-d. In some embodiments, even if physical
interaction is still required and/or desired (e.g., to initiate
voice-activation features), the ability to identify particular
voice commands 140 (e.g., originating from a specific user) may
reduce the occurrence of false command identification and/or
execution. In other words, voice-activation features may, according
to some embodiments, be more efficiently and/or correctly executed
regardless of how they are initiated.
[0022] Referring now to FIG. 2, a method 200 according to some
embodiments is shown. In some embodiments, the method 200 may be
conducted by and/or by utilizing the system 100 and/or may be
otherwise associated with the system 100 and/or any of the system
components described in conjunction with FIG. 1. The method 200
may, for example, be performed by and/or otherwise associated with
a user device 110a-d described herein. The flow diagrams described
herein do not necessarily imply a fixed order to the actions, and
embodiments may be performed in any order that is practicable. Note
that any of the methods described herein may be performed by
hardware, software (including microcode), firmware, manual means,
or any combination thereof. For example, a storage medium may store
thereon instructions that when executed by a machine result in
performance according to any of the embodiments described
herein.
[0023] In some embodiments, the method 200 may begin at 202 by
receiving voice input. For example, a user device (such as a user
device 110a-d) may receive voice input from one or more users
and/or other sources. In some embodiments, other voice sounds
and/or non-voice sounds may also be received. Voice input may,
according to some embodiments, be received via a microphone and/or
may otherwise include the receipt of a signal. The voice input may,
for example, be received via sound waves (e.g., through a medium
such as the air) and/or via other signals, waves, pulses, tones,
and/or other types of communication.
[0024] At 204, the method 200 may continue by determining if the
voice input is associated with a recognized user. The voice input
received at 202 may, for example, be analyzed, manipulated, and/or
otherwise processed to determine if the voice input is associated
with a known, registered, and/or recognized user. In some
embodiments, such as where the voice input is received by a user
device, the user device may conduct and/or participate in a process
to learn how to determine if voice input is associated with a
recognized user. The user of a user device such as a cell phone
may, for example, teach the cell phone how to recognize the user's
voice. In some embodiments, the user may speak various words and/or
phrases to the device and/or may otherwise take actions that may
facilitate recognition of the user's voice by the device. In some
embodiments, the learning process may be conducted for any number
of potential users of the device (e.g., various family members that
may use a single cell phone).
[0025] According to some embodiments, when voice input is received
by the user device, the user device may utilize information
gathered during the learning process to identify the user's voice.
The user's voice and/or speech pattern may, for example, be
compared to received voice and/or sound input to determine if
and/or when the user is speaking. In some embodiments, such a
capability may permit the device to distinguish the user's voice
from various other sounds that may be present in the device's
operating environment. The device may not require physical input
from the user to activate voice-activation features, for example,
because the device is capable of utilizing the user's voice as an
indicator of voice-activation initiation. Similarly, even if
physical input is required and/or desired to initiate
voice-activation features, once they are activated, the device may
be less likely to accept and/or process sounds from sources other
than the user.
[0026] In some embodiments, the method 200 may continue by
determining, in the case that the voice input is associated with
the recognized user, a command associated with the voice input. For
example, a user device may not only receive voice input from a
user, it may also process the received input to determine if the
input includes a command intended for the device. According to some
embodiments, once the device determines that the voice input is
associated with the recognized user, the device may analyze the
input to identify any commands within and/or otherwise associated
with the input.
[0027] For example, the user device may parse the voice input
(e.g., into individual words) and separately analyze the parsed
portions. In some embodiments, any portions within the voice input
may be compared to a stored list of pre-defined commands. If a
portion of the voice input matches a stored command, then the
stored command may, for example, be identified by the user device.
According to some embodiments, multiple commands may be received
within and/or identified as being associated with the voice input.
Stored and/or recognized commands may include any type of commands
that are or become know or practicable. Commands may include, for
example, letters, numbers, words, phrases, and/or other voice
sounds.
[0028] In some embodiments, commands may also or alternatively be
identified using other techniques. For example, the user device may
examine portions of the voice input to infer one or more commands.
The natural language of the voice input may, according to some
embodiments, be analyzed to determine a meaning associated with the
voice input (and/or a portion thereof). The meaning and/or intent
of a sentence may, for example, be determined and compared to
possible commands to identify one or more commands. In some
embodiments, the tone, inflection, and/or other properties of the
voice input may also or alternatively be analyzed to determine if
any relation to a potential commands exists.
[0029] The method 200 may continue, according to some embodiments,
by executing the command, at 208. The one or more commands
determined at 206 may, for example, be executed and/or otherwise
processed (e.g., by the user device). In some embodiments, the
command may be a voice-activation command. The voice-activation
features of the user device may, for example, be activated and/or
initiated in accordance with the method 200. Hands-free operation
of the device may, in some embodiments, be possible at least in
part because voice-activation commands may be executed without
requiring physical interaction between the user and the user
device. In some embodiments, even if hands-free operation is not
utilized, the commands executed at 208 may be more likely to be
accurate (e.g., compared to pervious systems) at least because the
voice input may be determined at 204 to be associated with a
recognized user (e.g., as opposed to accepting voice input
originating from any source).
[0030] Turning now to FIG. 3, a method 300 according to some
embodiments is shown. In some embodiments, the method 300 may be
conducted by and/or by utilizing the system 100 and/or may be
otherwise associated with the system 100 and/or any of the system
components described in conjunction with FIG. 1. The method 300
may, for example, be performed by and/or otherwise associated with
a user device 110a-d described herein. In some embodiments, the
method 300 may be associated with the method 200 described in
conjunction with FIG. 2.
[0031] According to some embodiments, the method 300 may begin at
302 by receiving voice input. The voice input may, for example, be
similar to the voice input received at 202. In some embodiments,
the voice input may be received via any means that is or becomes
known or practicable. According to some embodiments, the voice
input may include one or more commands (such as voice-activation
commands). In some embodiments, the voice input may be received
from and/or may be associated with any user and/or other entity.
According to some embodiments, the voice input may be received from
multiple sources.
[0032] The method 300 may continue, in some embodiments, by
determining if the voice input is associated with a recognized
activation identifier, at 304. According to some embodiments, a
user device may be assigned and/or otherwise associated with a
particular activation identifier. The device may, for example, be
given a name such as "Bob" or "Sue" and/or other assigned other
word identifiers such as "Alpha" or "Green". In some embodiments,
the user device may be identified by any type and/or configuration
of identifier that is or becomes known. According to some
embodiments, an activation identifier may include a phrase, number,
and/or other identifier. According to some embodiments, the
activation identifier may be substantially unique and/or may
otherwise easily distinguish one user device from another.
[0033] At 306, the method 300 may continue, for example, by
initiating an activation state in the case that the voice input is
associated with the recognized activation identifier. Upon
receiving and identifying a specific activation identifier (such as
"Alpha"), for example, a user device may become active and/or
initiate voice-activation features. In some embodiments, the
receipt of the activation identifier may take the place of
requiring physical interaction with the user device in order to
initiate voice-activation features. According to some embodiments,
the activation identifier may be received from any source. In other
words, anyone that knows the "name" of the user device may speak
the name to cause the device to enter an activation state (e.g., a
state where the device may "listen" for voice commands).
[0034] In some embodiments, the method 300 may also include a
determination of whether or not the activation identifier was
provided by a recognized user. The determination may, for example,
be similar to the determination at 204 in the method 200 described
herein. According to some embodiments, only activation identifiers
received from recognized users may cause the user device to enter
an activation state. Unauthorized users that know the device's
name, for example, may not be able to activate the device. In some
embodiments, such as where any user may activate the device by
speaking the device's name (e.g., the activation identifier), once
the device is activated it may "listen" for commands (e.g.,
voice-activation commands). According to some embodiments, the
device may only accept and/or execute commands that are received
from a recognized user. Even if an unrecognized user is able to
activate the device, for example, in some embodiments only a
recognized user may be able to cause the device to execute voice
commands.
[0035] In some embodiments, the use of the activation identifier to
activate the device may reduce the amount of power consumed by the
device in the inactive state (e.g., prior to initiation of the
activation state at 306). In the case that the device is only
required to "listen" for the activation identifier (e.g., as
opposed to any possible voice-activation command), for example, the
device may utilize a process that consumes a small amount of power.
An algorithm used to determine the activation identifier (such as
"Alpha) may, for example, be a relatively simple algorithm that is
only capable of determining a small sub-set of voice input (e.g.,
the activation identifier). In the case that the inactive device is
only required to identify the word "Alpha", for example, the device
may utilize a low Million Instructions Per Second (MIPS) algorithm
that is capable of identifying the single word of the activation
identifier. In some embodiments, once the activation identifier has
been determined using the low-power, low MIPS, and/or low
complexity algorithm, the device may switch to and/or otherwise
implement one or more complex algorithms capable of determining any
number of voice-activation commands.
[0036] Turning now to FIG. 4, a perspective diagram of an exemplary
system 400 according to some embodiments is shown. The system 400
may, for example, be utilized to implement and/or perform the
methods 200, 300 described herein and/or may be associated with the
system 100 described in conjunction with any of FIG. 1, FIG. 2,
and/or FIG. 3. In some embodiments, fewer or more components than
are shown in FIG. 4 may be included in the system 400. According to
some embodiments, different types, layouts, quantities, and
configurations of systems may be used.
[0037] The system 400 may include, for example, one or more users
402, 404, 406 and/or one or more user devices 410a-e. In some
embodiments, the users 402, 404, 406 may be associated with and/or
produce various voice sounds 430 and/or voice commands 442, 444.
The system 400 may, according to some embodiments, be or include an
environment such as a room and/or other area. In some embodiments,
the system 400 may include one or more objects such as a table 450.
For example, the system 400 may be a room in which several user
devices 410a-e are placed on the table 450. The three users 402,
404, 406 may also be present in the room and may speak to one
another and/or otherwise create and/or produce various voice sounds
430 and/or voice commands 442, 444.
[0038] In some embodiments, the first user 402 may, for example,
utter a first voice command 442 that includes the sentence "Save
Sue's e-mail address." The first voice command 442 may, for
example, be directed to the first user device 410a (e.g., the
laptop computer). The laptop 410a may, for example, be associated
with the first user 402 (e.g., the first user 402 may own and/or
otherwise operate the laptop 410a and/or may be a recognized user
of the laptop 410a). According to some embodiments, the laptop 410a
may recognize the voice of the first user 402 and may, for example,
accept and/or process the first voice command 442. In some
embodiments, the second and third users 404, 406 may also be
talking.
[0039] The third user 406 may, for example, utter a voice sound 430
that includes the sentences shown in FIG. 4. According to some
embodiments, the laptop 410a may be capable of distinguishing the
first voice command 442 (e.g., the command intended for the laptop
410a) from the other voice sounds 430 and/or voice commands 444
within the environment. Even though the voice sounds 430 may
include pre-defined command words (such as "call" and "save"), for
example, the laptop 410a may ignore such commands because they do
not originate from the first user 402 (e.g., the user recognized by
the laptop 410a).
[0040] In some embodiments, the third user 406 may be a recognized
user of the laptop 410a (e.g., the third user 406 may be the spouse
of the first user 402 and both may operate the laptop 410a). The
laptop 410a may, for example, recognize and/or process the voice
sounds 430 made by the third user 406 in the case that the third
user 406 is a recognized user. According to some embodiments, voice
sounds 430 and/or commands 442 from multiple recognized users
(e.g., the first and third users 402, 406) may be accepted and/or
processed by the laptop 410a. In some embodiments, the laptop 410a
may prioritize and/or choose one or more commands to execute (such
as in the case that commands are conflict).
[0041] According to some embodiments, the laptop 410a may analyze
the first voice command 442 (e.g., the command received from the
recognized first user 402). The laptop 410a may, for example,
identify a pre-defined command word "save" within the first voice
command 442. The laptop 410a may also or alternatively analyze the
first voice command 442 to determine the meaning of speech provided
by the first user 402. For example, the laptop 410a may analyze the
natural language of the first voice command 442 to determine one or
more actions the laptop 410a is desired to take.
[0042] The laptop 410a may, in some embodiments, determine that the
first user 402 wishes that the e-mail address associated with the
name "Sue" be saved. The laptop 410a may then, for example,
identify an e-mail address associated with and/or containing the
name "Sue" and may store the address. In some embodiments, such as
in the case that the analysis of the natural language may indicate
multiple potential actions that the laptop 410a should take, the
laptop 410a may select one of the actions (e.g., based on priority
or likelihood based on context), prompt the first user 402 for more
input (e.g., via a display screen or through a voice prompt),
and/or await further clarifying instructions from the first user
402.
[0043] In some embodiments, the second user 404 may also or
alternatively be speaking. The second user 404 may, for example,
provide the second voice command 444, directed to the second user
device 410b (e.g., one of the cellular telephones). According to
some embodiments, the cell phone 410b may be configured to enter an
activation state in response to an activation identifier. The cell
phone 410b may, for example, be associated with, labeled, and/or
named "Alpha". The second user 404 may, in some embodiments (such
as shown in FIG. 4), speak an initial portion of a second voice
command 444a that includes the phrase "Alpha, activate."
[0044] According to some embodiments, when the cell phone 410b
"hears" its "name" (e.g., Alpha), it may enter an activation state
in which it actively listens for (and/or is otherwise activated to
accept) further voice commands. In some embodiments, the cell phone
410b may enter an activation state when it detects a particular
combination of words and/or sounds. The cell phone 410b may require
the name Alpha to be spoken, followed by the command "activate",
for example, prior to entering an activation state. In some
embodiments (such as where the device's name is a common name such
as "Bob"), the additional requirement of detecting the command
"activate" may reduce the possibility of the cell phone activating
due to voice sounds not directed to the device (e.g., when someone
in the environment is speaking to a person named Bob).
[0045] In some embodiments, the second user 404 may also or
alternatively speak a second portion of the second voice command
444b. After the cell phone 410b is activated, for example (e.g., by
receiving the first portion of the second voice command 444a), the
second user 404 may provide a command, such as "Dial, 9-239 . . . "
to the cell phone 410b. According to some embodiments, the second
portion of the second voice command 444b may not need to be
prefaced with the name (e.g., Alpha) of the cell phone 410b. For
example, once the cell phone 410b is activated (e.g., by receiving
the first portion of the second voice command 444a) it may stay
active (e.g., continue to actively monitor for and/or be receptive
to voice commands) for a period of time.
[0046] In some embodiments, the activation period may be
pre-determined (e.g., a thirty-second period) and/or may be
determined based on the environment and/or other context (e.g., the
cell phone 410b may stay active for five seconds after voice
commands have stopped being received). According to some
embodiments, during the activation period (e.g., while the cell
phone 410b is in an activation state), the cell phone 410b may only
be responsive to commands received from a recognized user (e.g.,
the second user 404). Any user 402, 404, 406 may, for example,
speak the name of the cell phone 410b to activate the cell phone
410b, but then only the second user 404 may be capable of causing
the cell phone 410b to execute commands. According to some
embodiments, even the activation identifier may need to be received
from the second user 404 for the cell phone 410b to enter the
activation state.
[0047] Referring now to FIG. 5, a block diagram of a system 500
according to some embodiments is shown. The system 500 may, for
example, be utilized to implement and/or perform the methods 200,
300 described herein and/or may be associated with the systems 100,
400 described in conjunction with any of FIG. 1, FIG. 2, FIG. 3,
and/or FIG. 4. In some embodiments, fewer or more components than
are shown in FIG. 5 may be included in the system 500. According to
some embodiments, different types, layouts, quantities, and
configurations of systems may be used.
[0048] In some embodiments, the system 500 may be or include a
wireless communication device such as a wireless telephone, a
laptop computer, or a PDA. According to some embodiments, the
system 500 may be or include a user device such as the user devices
110a-d, 410a-e described herein. The system 500 may include, for
example, one or more control circuits 502, which may be any type or
configuration of processor, microprocessor, micro-engine, and/or
any other type of control circuit that is or becomes known or
available. In some embodiments, the system 500 may also or
alternatively include an antenna 504, a speaker 506, a microphone
508, a power supply 510, a connector 512, and/or a memory 514, all
and/or any of which may be in communication with the control
circuit 502. The memory 514 may store, for example, code and/or
other instructions operable to cause the control circuit 502 to
perform in accordance with embodiments described herein.
[0049] The antenna 504 may be any type and/or configuration of
device for transmitting and/or receiving communications signals
that is or becomes known. The antenna 504 may protrude from the top
of the system 500 as shown in FIG. 5 or may also or alternatively
be internally located, mounted on any other exterior portion of the
system 500, or may be integrated into the structure or body 516 of
the wireless device itself. The antenna 504 may, according to some
embodiments, be configured to receive any number of communications
signals that are or become known including, but not limited to,
Radio Frequency (RF), Infrared Radiation (IR), satellite, cellular,
optical, and/or microwave signals.
[0050] The speaker 506 and/or the microphone 508 may be or include
any types and/or configurations of devices that are capable of
producing and capturing sounds, respectively. In some embodiments,
the speaker 506 may be situated to be positioned near a user's ear
during use of the system 500, while the microphone 508 may, for
example, be situated to be positioned near a user's mouth.
According to some embodiments, fewer or more speakers 506 and/or
microphones 508 may be included in the system 500. In some
embodiments, the microphone 508 may be configured to receive sounds
and/or other signals such as voice sounds or voice commands as
described herein (e.g., voice sounds 130, 430 and/or voice commands
140, 442, 444).
[0051] The power supply 510 may, in some embodiments, be integrated
into, removably attached to any portion of, and/or be external to
the system 500. The power supply 510 may, for example, include one
or more battery devices that are removably attached to the back of
a wireless device such as a cellular telephone. The power supply
510 may, according to some embodiments, provide Alternating Current
(AC) and/or Direct Current (DC), and may be any type or
configuration of device capable of delivering power to the system
500 that is or becomes known or practicable. In some embodiments,
the power supply 510 may interface with the connector 512. The
connector 512 may, for example, allow the system 500 to be
connected to external components such as external speakers,
microphones, and/or battery charging devices. According to some
embodiments, the connector 512 may allow the system 500 to receive
power from external sources and/or may provide recharging power to
the power supply 510.
[0052] In some embodiments, the memory 514 may store any number
and/or configuration of programs, modules, procedures, and/or other
instructions that may, for example, be executed by the control
circuit 502. The memory 514 may, for example, include logic that
allows the system 500 to learn, identify, and/or otherwise
determine the voice sounds and/or voice commands of one or more
particular users (e.g., recognized users). In some embodiments, the
memory 514 may also or alternatively include logic that allows the
system 500 to identify one or more activation identifiers and/or to
interpret the natural language of speech.
[0053] According to some embodiments, the memory 514 may store a
database, tables, lists, and/or other data that allow the system
500 to identify and/or otherwise determine executable commands. The
memory 514 may, for example, store a list of recognizable commands
that may be compared to received voice input to determine actions
that the system 500 is desired to perform. In some embodiments, the
memory 514 may store other instructions such as operation and/or
command execution rules, security features (e.g., passwords),
and/or user profiles.
[0054] Turning now to FIG. 6, a block diagram of a system 600
according to some embodiments is shown. The system 600 may, for
example, be utilized to implement and/or perform the methods 200,
300 described herein and/or may be associated with the systems 100,
400, 500 described in conjunction with any of FIG. 1, FIG. 2, FIG.
3, FIG. 4, and/or FIG. 5. In some embodiments, fewer or more
components than are shown in FIG. 6 may be included in the system
600. According to some embodiments, different types, layouts,
quantities, and configurations of systems may be used.
[0055] In some embodiments, the system 600 may be or include a
communication device such as a PC, a PDA, a wireless telephone,
and/or a notebook computer. According to some embodiments, the
system 600 may be a user device such as the user devices 110a-d,
410a-e described herein. In some embodiments, the system 600 may be
a wireless communication device (such as the system 500) that is
used to provide hands-free voice-activation features to a user. The
system 600 may include, for example, one or more processors 602,
which may be any type or configuration of processor,
microprocessor, and/or micro-engine that is or becomes known or
available. In some embodiments, the system 600 may also or
alternatively include a communication interface 604, an input
device 606, an output device 608, and/or a memory device 610, all
and/or any of which may be in communication with the processor 602.
The memory device 610 may store, for example, an activation module
612 and/or a language module 614.
[0056] The communication interface 604, the input device 606,
and/or the output device 608 may be or include any types and/or
configurations of devices that are or become known or available.
According to some embodiments, the input device 606 may include a
keypad, one or more buttons, and/or one or more softkeys and/or
variable function input devices. The input device 606 may include,
for example, any input component of a wireless telephone and/or PDA
device, such as a touch screen and/or a directional pad or
button.
[0057] The memory device 610 may be or include, according to some
embodiments, one or more magnetic storage devices, such as hard
disks, one or more optical storage devices, and/or solid state
storage. The memory device 610 may store, for example, the
activation module 612 and/or the language module 614. The modules
612, 614 may be any type of applications, modules, programs, and/or
devices that are capable of facilitating hands-free
voice-activation. Either or both of the activation module 612 and
the language module 614 may, for example, include instructions that
cause the processor 602 to operate the system 600 in accordance
with embodiments as described herein.
[0058] For example, the activation module 612 may include
instructions that are operable to cause the system 600 to enter an
activation state in response to received voice input. The
activation module 612 may, in some embodiments, cause the processor
602 to conduct the one or both of the methods 200, 300 described
herein. According to some embodiments, the activation module 612
may, for example, cause the system 600 to enter an activation state
in the case that voice sounds and/or voice commands are received
from a recognized user and/or that include a particular activation
identifier (e.g., a name associated with the system 600).
[0059] In some embodiments, the language module 614 may identify
and/or interpret the voice input that has been received (e.g., via
the input device 606 and/or the communication interface 604). The
language module 614 may, for example, determine that received voice
input is associated with a recognized user and/or determine one or
more commands that may be associated with the voice input.
According to some embodiments, the language module 614 may also or
alternatively analyze the natural language of the voice input
(e.g., to determine commands associated with the voice input). In
some embodiments, such as in the case that the activation module
612 causes the system 600 to become activated, the language module
614 may identify and/or execute voice commands (e.g.,
voice-activation commands).
[0060] The several embodiments described herein are solely for the
purpose of illustration. Those skilled in the art will note that
various substitutions may be made to those embodiments described
herein without departing from the spirit and scope of the present
invention. Those skilled in the art will also recognize from this
description that other embodiments may be practiced with
modifications and alterations limited only by the claims.
* * * * *